Intelligent Generation of Image-Like Representations of Ordered and Heterogenous Data to Enable Explainability of Artificial Intelligence Results

1. A method, by a processor, for providing intelligent generation of image-like representation of ordered and heterogenous data to enable explainability of artificial intelligence results in a computing environment, comprising: transforming one or more data sets into one or more pseudo-image representations to enable one or more image processing tasks for image processing; and providing an interpretation of an image processing task result from applying the one or more image processing tasks on the one or more pseudo-image representations generated from one or more data sets, wherein providing the interpretation includes analyzing an output of the image processing task result to identify those of one or more data points of the one or more pseudo-image representations that most likely contributed to a classification of the output of the image processing task result, and returning to analyze those of the one or more data points as input into the one or more image processing tasks to generate a human-understandable interpretation as to a reasoning for the classification.

2. The method of claim 1 , further including: defining the one or more pseudo-image representations to include one or more elements, wherein the one or more elements include a value and a set of coordinates specifying a position of the one or more elements within the one or more pseudo-image representations; and mapping the one or more elements to the one or more data points in the one or more pseudo-image representations.

3. The method of claim 1 , further including initiating a machine learning operation to learn and train a machine learning model to transform the one or more data sets into one or more pseudo-image representations.

4. A system for intelligent generation of image-like representation of ordered and heterogenous data to enable explainability of artificial intelligence results in a computing environment, comprising: one or more computers with executable instructions that when executed cause the system to: transform one or more data sets into one or more pseudo-image representations to enable one or more image processing tasks for image processing; and provide an interpretation of an image processing task result from applying the one or more image processing tasks on the one or more pseudo-image representations generated from one or more data sets, wherein providing the interpretation includes analyzing an output of the image processing task result to identify those of one or more data points of the one or more pseudo-image representations that most likely contributed to a classification of the output of the image processing task result, and returning to analyze those of the one or more data points as input into the one or more image processing tasks to generate a human-understandable interpretation as to a reasoning for the classification.

5. The system of claim 4 , wherein the executable instructions further: define the one or more pseudo-image representations to include one or more elements, wherein the one or more elements include a value and a set of coordinates specifying a position of the one or more elements within the one or more pseudo-image representations; and map the one or more elements to the one or more data points in the one or more pseudo-image representations.

6. The system of claim 4 , wherein the executable instructions further initiate a machine learning operation to learn and train a machine learning model to transform the one or more data sets into one or more pseudo-image representations.

7. A computer program product for providing intelligent generation of image-like representation of ordered and heterogenous data to enable explainability of artificial intelligence results by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising: an executable portion that transforms one or more data sets into one or more pseudo-image representations to enable one or more image processing tasks for image processing; and an executable portion that provides an interpretation of an image processing task result from applying the one or more image processing tasks on the one or more pseudo-image representations generated from one or more data sets, wherein providing the interpretation includes analyzing an output of the image processing task result to identify those of one or more data points of the one or more pseudo-image representations that most likely contributed to a classification of the output of the image processing task result, and returning to analyze those of the one or more data points as input into the one or more image processing tasks to generate a human-understandable interpretation as to a reasoning for the classification.

8. The computer program product of claim 7 , further including an executable portion that: defines the one or more pseudo-image representations to include one or more elements, wherein the one or more elements include a value and a set of coordinates specifying a position of the one or more elements within the one or more pseudo-image representations; and maps the one or more elements to the one or more data points in the one or more pseudo-image representations.

9. The computer program product of claim 7 , further including an executable portion that initiates a machine learning operation to learn and train a machine learning model to transform the one or more data sets into one or more pseudo-image representations.